Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1161730AbXEBGRp (ORCPT ); Wed, 2 May 2007 02:17:45 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1161754AbXEBGRp (ORCPT ); Wed, 2 May 2007 02:17:45 -0400 Received: from mga03.intel.com ([143.182.124.21]:59499 "EHLO mga03.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1161730AbXEBGRm (ORCPT ); Wed, 2 May 2007 02:17:42 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.14,477,1170662400"; d="scan'208";a="222855664" From: Dan Williams Subject: [PATCH 06/16] md: use raid5_run_ops for stripe cache operations To: neilb@suse.de, akpm@linux-foundation.org, christopher.leech@intel.com Cc: linux-kernel@vger.kernel.org, linux-raid@vger.kernel.org Date: Tue, 01 May 2007 23:17:41 -0700 Message-ID: <20070502061741.7066.21778.stgit@dwillia2-linux.ch.intel.com> In-Reply-To: <20070502060949.7066.357.stgit@dwillia2-linux.ch.intel.com> References: <20070502060949.7066.357.stgit@dwillia2-linux.ch.intel.com> User-Agent: StGIT/0.12.1 MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4905 Lines: 149 Each stripe has three flag variables to reflect the state of operations (pending, ack, and complete). -pending: set to request servicing in raid5_run_ops -ack: set to reflect that raid5_runs_ops has seen this request -complete: set when the operation is complete and it is ok for handle_stripe5 to clear 'pending' and 'ack'. Signed-off-by: Dan Williams --- drivers/md/raid5.c | 65 +++++++++++++++++++++++++++++++++++++++++++++------- 1 files changed, 56 insertions(+), 9 deletions(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 0251bca..14e9f6a 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -126,6 +126,7 @@ static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh) } md_wakeup_thread(conf->mddev->thread); } else { + BUG_ON(sh->ops.pending); if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) { atomic_dec(&conf->preread_active_stripes); if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) @@ -225,7 +226,8 @@ static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx, int BUG_ON(atomic_read(&sh->count) != 0); BUG_ON(test_bit(STRIPE_HANDLE, &sh->state)); - + BUG_ON(sh->ops.pending || sh->ops.ack || sh->ops.complete); + CHECK_DEVLOCK(); PRINTK("init_stripe called, stripe %llu\n", (unsigned long long)sh->sector); @@ -241,11 +243,11 @@ static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx, int for (i = sh->disks; i--; ) { struct r5dev *dev = &sh->dev[i]; - if (dev->toread || dev->towrite || dev->written || + if (dev->toread || dev->read || dev->towrite || dev->written || test_bit(R5_LOCKED, &dev->flags)) { - printk("sector=%llx i=%d %p %p %p %d\n", + printk("sector=%llx i=%d %p %p %p %p %d\n", (unsigned long long)sh->sector, i, dev->toread, - dev->towrite, dev->written, + dev->read, dev->towrite, dev->written, test_bit(R5_LOCKED, &dev->flags)); BUG(); } @@ -325,6 +327,43 @@ static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector return sh; } +/* check_op() ensures that we only dequeue an operation once */ +#define check_op(op) do {\ + if (test_bit(op, &sh->ops.pending) &&\ + !test_bit(op, &sh->ops.complete)) {\ + if (test_and_set_bit(op, &sh->ops.ack))\ + clear_bit(op, &pending);\ + else\ + ack++;\ + } else\ + clear_bit(op, &pending);\ +} while(0) + +/* find new work to run, do not resubmit work that is already + * in flight + */ +static unsigned long get_stripe_work(struct stripe_head *sh) +{ + unsigned long pending; + int ack = 0; + + pending = sh->ops.pending; + + check_op(STRIPE_OP_BIOFILL); + check_op(STRIPE_OP_COMPUTE_BLK); + check_op(STRIPE_OP_PREXOR); + check_op(STRIPE_OP_BIODRAIN); + check_op(STRIPE_OP_POSTXOR); + check_op(STRIPE_OP_CHECK); + if (test_and_clear_bit(STRIPE_OP_IO, &sh->ops.pending)) + ack++; + + sh->ops.count -= ack; + BUG_ON(sh->ops.count < 0); + + return pending; +} + static int raid5_end_read_request(struct bio * bi, unsigned int bytes_done, int error); static int @@ -1878,7 +1917,6 @@ static int stripe_to_pdidx(sector_t stripe, raid5_conf_t *conf, int disks) * schedule a write of some buffers * return confirmation of parity correctness * - * Parity calculations are done inside the stripe lock * buffers are taken off read_list or write_list, and bh_cache buffers * get BH_Lock set before the stripe lock is released. * @@ -1896,10 +1934,11 @@ static void handle_stripe5(struct stripe_head *sh) int non_overwrite = 0; int failed_num=0; struct r5dev *dev; + unsigned long pending=0; - PRINTK("handling stripe %llu, cnt=%d, pd_idx=%d\n", - (unsigned long long)sh->sector, atomic_read(&sh->count), - sh->pd_idx); + PRINTK("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d ops=%lx:%lx:%lx\n", + (unsigned long long)sh->sector, sh->state, atomic_read(&sh->count), + sh->pd_idx, sh->ops.pending, sh->ops.ack, sh->ops.complete); spin_lock(&sh->lock); clear_bit(STRIPE_HANDLE, &sh->state); @@ -2349,8 +2388,14 @@ static void handle_stripe5(struct stripe_head *sh) } } + if (sh->ops.count) + pending = get_stripe_work(sh); + spin_unlock(&sh->lock); + if (pending) + raid5_run_ops(sh, pending); + while ((bi=return_bi)) { int bytes = bi->bi_size; @@ -3847,8 +3892,10 @@ static void raid5d (mddev_t *mddev) handled++; } - if (list_empty(&conf->handle_list)) + if (list_empty(&conf->handle_list)) { + async_tx_issue_pending_all(); break; + } first = conf->handle_list.next; sh = list_entry(first, struct stripe_head, lru); - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/